© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78457
    Prev
    Next
    INDEX
    Explanations

    academic journal names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esercizi
    0.42
     резер
    0.41
     нормально
    0.40
    ப்படாத
    0.40
    ᷅
    0.39
    ংকর
    0.38
     RESERVE
    0.38
     équ
    0.37
     finales
    0.37
    羵
    0.37
    POSITIVE LOGITS
    ">//
    0.36
    obtained
    0.36
    toned
    0.35
     glide
    0.34
    carried
    0.34
    distributed
    0.34
    感覚
    0.33
    ဂျ
    0.33
    koj
    0.33
    ലാണ്
    0.33
    Activations Density 0.000%

    No Known Activations